{
  "schema_version": "1.1",
  "provider": "sio",
  "dataset": "pic-zooplankton",
  "workflow": "https://calcofi.io/workflows/ingest_sio_pic-zooplankton.html",
  "tables": {
    "sample": {
      "name_long": "Sample",
      "description_md": "One row per physical sampling event at its native grain (site, tow, net, cast, bottle, underway, transect, region pool). An adjacency list: `parent_sample_key` points at the containing event and `root_sample_key` at the top of the chain, so counting distinct events at any level is a single `GROUP BY`."
    },
    "dataset": {
      "name_long": "Dataset",
      "description_md": ""
    }
  },
  "columns": {
    "dataset.provider": {
      "name_long": "Provider",
      "units": null,
      "description_md": ""
    },
    "dataset.dataset": {
      "name_long": "Dataset",
      "units": null,
      "description_md": ""
    },
    "dataset.dataset_name": {
      "name_long": "Dataset Name",
      "units": null,
      "description_md": ""
    },
    "dataset.dataset_name_short": {
      "name_long": "Dataset Name Short",
      "units": null,
      "description_md": ""
    },
    "dataset.category": {
      "name_long": "Category",
      "units": null,
      "description_md": ""
    },
    "dataset.color": {
      "name_long": "Color",
      "units": null,
      "description_md": ""
    },
    "dataset.description": {
      "name_long": "Description",
      "units": null,
      "description_md": ""
    },
    "dataset.citation_main": {
      "name_long": "Citation Main",
      "units": null,
      "description_md": ""
    },
    "dataset.citation_others": {
      "name_long": "Citation Others",
      "units": null,
      "description_md": ""
    },
    "dataset.link_calcofi_org": {
      "name_long": "Link Calcofi Org",
      "units": null,
      "description_md": ""
    },
    "dataset.link_data_source": {
      "name_long": "Link Data Source",
      "units": null,
      "description_md": ""
    },
    "dataset.link_others": {
      "name_long": "Link Others",
      "units": null,
      "description_md": ""
    },
    "dataset.tables": {
      "name_long": "Tables",
      "units": null,
      "description_md": ""
    },
    "dataset.coverage_temporal": {
      "name_long": "Coverage Temporal",
      "units": null,
      "description_md": ""
    },
    "dataset.coverage_spatial": {
      "name_long": "Coverage Spatial",
      "units": null,
      "description_md": ""
    },
    "dataset.license": {
      "name_long": "License",
      "units": null,
      "description_md": ""
    },
    "dataset.pi_names": {
      "name_long": "Pi Names",
      "units": null,
      "description_md": ""
    },
    "dataset.doi": {
      "name_long": "Doi",
      "units": null,
      "description_md": ""
    },
    "dataset.license_url": {
      "name_long": "License Url",
      "units": null,
      "description_md": ""
    },
    "dataset.acknowledgement": {
      "name_long": "Acknowledgement",
      "units": null,
      "description_md": ""
    },
    "dataset.contact": {
      "name_long": "Contact",
      "units": null,
      "description_md": ""
    },
    "sample.sample_key": {
      "name_long": "Sample Key",
      "description_md": "Globally unique event key, namespaced `dataset_key:sample_type:id` so the same integer id in two datasets — or at two event levels in one dataset — never collides."
    },
    "sample.sample_type": {
      "name_long": "Sample Type",
      "description_md": "Event grain: `site`, `tow`, `net`, `cast`, `bottle`, `underway`, `transect` or `region_pool`."
    },
    "sample.parent_sample_key": {
      "name_long": "Parent Sample Key",
      "description_md": "The containing event (net → tow → site; bottle → cast). NULL at the top of the chain. Flat adjacency list: attributes are not inherited."
    },
    "sample.root_sample_key": {
      "name_long": "Root Sample Key",
      "description_md": "Top of this event's containment chain; equals `sample_key` for single-level datasets. Use `count(DISTINCT root_sample_key)` to count stations/casts irrespective of grain."
    },
    "sample.dataset_key": {
      "name_long": "Dataset Key",
      "description_md": "Provenance stamp: `provider_dataset`."
    },
    "sample.grid_key": {
      "name_long": "Grid Key",
      "description_md": "CalCOFI station grid cell. NULL where the dataset has no station assignment (region-pooled phytoplankton)."
    },
    "sample.site_key": {
      "name_long": "Site Key",
      "description_md": "CalCOFI station natural key as the source records it (line/station, e.g. `090.0 060.0`). Present on 13 of the 18 source event tables, so it is carried on the event dimension rather than lost to consolidation; `grid_key` is the derived grid cell, this is the source's own station id."
    },
    "sample.cruise_key": {
      "name_long": "Cruise Key",
      "description_md": "CalCOFI cruise natural key `YYYY-MM-NODC`."
    },
    "sample.order_occ": {
      "name_long": "Order of Occupation",
      "description_md": "Order in which the station was occupied on the cruise. Source spelling varies (`order_occ`, `ord_occ`) and CTD stores it as text; normalised to an integer here."
    },
    "sample.latitude": {
      "name_long": "Latitude",
      "units": "decimal degrees",
      "description_md": "Event latitude (WGS84)."
    },
    "sample.longitude": {
      "name_long": "Longitude",
      "units": "decimal degrees",
      "description_md": "Event longitude (WGS84)."
    },
    "sample.datetime": {
      "name_long": "Datetime",
      "description_md": "Event start time (UTC)."
    },
    "sample.depth_min_m": {
      "name_long": "Depth Min",
      "units": "m",
      "description_md": "Shallowest depth sampled by this event."
    },
    "sample.depth_max_m": {
      "name_long": "Depth Max",
      "units": "m",
      "description_md": "Deepest depth sampled by this event."
    },
    "sample.tow_type": {
      "name_long": "Tow Type",
      "description_md": "Net gear code where the dataset records one (C1/CB/CV/PV oblique or vertical, MT manta); NULL for gears and datasets without one. Needed to compute gear-appropriate CPUE."
    },
    "sample.data_stage": {
      "name_long": "Data Stage",
      "description_md": "The source's own processing state for this event: `final` (post-cruise calibrations applied) or `preliminary` (**not for publication** — the source warns that oxygen, nitrate and chlorophyll may change significantly once calibrated). Populated by `calcofi_ctd-cast`; NULL where the dataset draws no such distinction, which is not a claim that the data are final."
    },
    "sample.geom": {
      "name_long": "Geometry",
      "description_md": "Point geometry minted from `longitude`/`latitude` (OGC:CRS84)."
    },
    "sample.source_uuid": {
      "name_long": "Source Uuid",
      "units": null,
      "description_md": ""
    }
  },
  "contributions": {
    "sample": {
      "rows": 82343,
      "owned": true,
      "shared": true
    }
  }
}